© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10365
    Prev
    Next
    INDEX
    Explanations

    words indicating desire, choice, or planning

    oai_token-act-pair · gemini-2.0-flash

    desires and expectations

    np_max-act · gemini-2.0-flash

    hopes

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wants
    -1.27
     wants
    -1.26
     knows
    -1.24
     hopes
    -1.24
    wants
    -1.16
     loves
    -1.13
    knows
    -1.11
     understands
    -1.05
     likes
    -1.03
     Loves
    -1.01
    POSITIVE LOGITS
    ловек
    0.42
     Unidos
    0.42
    izr
    0.41
     stubble
    0.41
     mắn
    0.40
    ỏ
    0.40
    onucleotides
    0.40
     suppose
    0.40
     jsPsych
    0.40
    getItemId
    0.40
    Activations Density 3.884%

    No Known Activations